What are the most popular Claude Code skills?

Ranked by real invocations measured from developers' local agent transcripts, the skills at the top of this page are the ones developers actually run — not the ones with the most GitHub stars or directory listings. The ranking updates as new usage syncs in.

Which MCP servers do developers actually use?

The tool-call table on this page separates MCP server calls (named like server · tool) from built-in agent tools, ranked by real call counts, token burn and error rates measured from local transcripts.

How is skill and tool usage measured?

The whoburnedmore CLI parses the transcripts coding agents keep locally and submits only name + count + token aggregates for skills and tool calls. No prompts, arguments, file names or outputs are collected.

Most-Used Claude Code Skills & MCP Servers — Real Usage Data

SKILLS+MCP

LIVE · 2026-11-13 17:15Z

Skills tracked

100

Skill invocations

940,178

MCP tools

Built-in tools

Tool calls

10,056,801

Developers

221

listed panel

Skills by real usage

100 skills · row fill = vs top skill

#	Skill	Devs	Calls	Tokens
01	superpowers:writing-plans	31	33,533	9.11B
02	workflow-authoring	24	55,939	8.18B
03	code-review	57	51,998	8.03B

MCP server tools

50 tools · server · tool

#	MCP tool	Devs	Calls	Tokens	Err
01	claude-in-chrome · browser_batch	79	35,752	10.21B	5%
02	ccd_turn · update_plan	67	61,457	9.74B

METHODOLOGY — measured, not surveyed: the open-source npx whoburnedmore CLI reads the local usage logs coding agents already keep and submits daily aggregate token totals per tool and model — never prompts, code or file names. Panel = 221 listed developers who opted in publicly, including subscription usage (Claude Code, Cursor, Codex) that API-gateway rankings never see. Costs estimated from public per-token pricing. what we collect · leaderboard · state of AI coding

Built-in agent tools

50 tools

#	Tool	Devs	Calls	Tokens	Err
01	Bash	281	4,803,333	991.15B	3%
02	exec	206	1,192,290	154.96B	0%
03	Read	281	885,770	120.35B	1%
04	Edit	273	453,463	105.82B	3%
05	Write	276	254,301	57.75B	2%
06	exec_command	121	667,904	36.86B	0%
07	WebFetch	251	184,563	17.62B	4%
08	apply_patch	131	114,707	14.46B	0%
09	Agent	239	56,817	13.63B	2%
10	WebSearch	240	118,146	10.43B	1%
11	ToolSearch	255	71,883	9.78B	0%
12	send_message	102	74,460	9.73B	0%
13	write_stdin	104	91,196	9.51B	0%
14	wait	169	62,415	8.47B	0%
15	shell_command	50	138,328	7.36B	0%
16	js	144	51,566	7.10B	0%
17	PowerShell	49	26,261	6.31B	12%
18	StructuredOutput	96	50,022	5.36B	9%
19	SendMessage	144	22,221	5.18B	0%
20	TaskUpdate	124	18,634	4.74B	0%
21	Monitor	186	16,731	4.54B	4%
22	Grep	121	46,683	4.43B	2%
23	SubagentHandback	115	21,302	4.22B	0%
24	AskUserQuestion	255	13,842	3.43B	7%
25	wait_agent	97	53,661	3.09B	0%
26	Artifact	149	10,519	2.92B	5%
27	Skill	244	18,712	2.81B	1%
28	TaskCreate	126	10,994	2.35B	1%
29	TaskStop	210	9,841	2.28B	4%
30	sleep	96	11,948	1.80B	0%
31	shell	10	21,968	1.76B	0%
32	view_file	2	4,692	1.57B	0%
33	SendUserFile	119	4,704	1.57B	2%
34	update_plan	105	13,290	1.48B	0%
35	manage_task	2	2,239	1.36B	0%
36	run_command	3	5,971	1.05B	0%
37	ScheduleWakeup	127	3,244	1.04B	2%
38	followup_task	80	8,271	891.5M	0%
39	Glob	98	24,635	874.1M	1%
40	Workflow	86	2,575	858.8M	6%
41	TodoWrite	33	3,855	790.0M	0%
42	spawn_agent	117	10,823	679.8M	0%
43	write_to_file	2	2,717	629.8M	0%
44	list_agents	87	6,201	596.5M	0%
45	view_image	86	6,561	567.5M	0%
46	replace_file_content	2	1,392	526.8M	0%
47	ArtifactData	24	2,325	420.4M	14%
48	run	17	3,324	377.9M	0%
49	request_user_input_async	116	2,783	364.1M	0%
50	ListAgents	98	1,352	343.0M	0%

SKILLS+MCP

▮Skills by real usage

▮MCP server tools

▮Built-in agent tools

Skills by real usage

MCP server tools

Built-in agent tools